Patents by Inventor Philip Bachman
Philip Bachman has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20230042546Abstract: Examples of the present disclosure provide systems and methods relating to a machine comprehension test with a learning-based approach, harnessing neural networks arranged in a parallel hierarchy. This parallel hierarchy enables the model to compare the passage, question, and answer from a variety of perspectives, as opposed to using a manually designed set of features. Perspectives may range from the word level to sentence fragments to sequences of sentences, and networks operate on word-embedding representations of text. A training methodology for small data is also provided.Type: ApplicationFiled: October 17, 2022Publication date: February 9, 2023Applicant: Microsoft Technology Licensing, LLCInventors: Adam TRISCHLER, Zheng YE, Xingdi YUAN, Philip BACHMAN
-
Patent number: 11507834Abstract: Examples of the present disclosure provide systems and methods relating to a machine comprehension test with a learning-based approach, harnessing neural networks arranged in a parallel hierarchy. This parallel hierarchy enables the model to compare the passage, question, and answer from a variety of perspectives, as opposed to using a manually designed set of features. Perspectives may range from the word level to sentence fragments to sequences of sentences, and networks operate on word-embedding representations of text. A training methodology for small data is also provided.Type: GrantFiled: May 12, 2020Date of Patent: November 22, 2022Assignee: Microsoft Technology Licensing, LLCInventors: Adam Trischler, Zheng Ye, Xingdi Yuan, Philip Bachman
-
Publication number: 20220327407Abstract: Described herein are systems and methods for providing a natural language comprehension system that employs a two-stage process for machine comprehension of text. The first stage indicates words in one or more text passages that potentially answer a question. The first stage outputs a set of candidate answers for the question, along with a first probability of correctness for each candidate answer. The second stage forms one or more hypotheses by inserting each candidate answer into the question and determines whether a sematic relationship exists between each hypothesis and each sentence in the text. The second processing circuitry generates a second probability of correctness for each candidate answer and combines the first probability with the second probability to produce a score that is used to rank the candidate answers. The candidate answer with the highest score is selected as a predicted answer.Type: ApplicationFiled: June 24, 2022Publication date: October 13, 2022Applicant: Microsoft Technology Licensing, LLCInventors: Adam TRISCHLER, Philip BACHMAN, Xingdi YUAN, Alessandro SORDONI, Zheng YE
-
Patent number: 11379736Abstract: Described herein are systems and methods for providing a natural language comprehension system that employs a two-stage process for machine comprehension of text. The first stage indicates words in one or more text passages that potentially answer a question. The first stage outputs a set of candidate answers for the question, along with a first probability of correctness for each candidate answer. The second stage forms one or more hypotheses by inserting each candidate answer into the question and determines whether a sematic relationship exists between each hypothesis and each sentence in the text. The second processing circuitry generates a second probability of correctness for each candidate answer and combines the first probability with the second probability to produce a score that is used to rank the candidate answers. The candidate answer with the highest score is selected as a predicted answer.Type: GrantFiled: May 17, 2017Date of Patent: July 5, 2022Assignee: Microsoft Technology Licensing, LLCInventors: Adam Trischler, Philip Bachman, Xingdi Yuan, Alessandro Sordoni, Zheng Ye
-
Publication number: 20200279161Abstract: Examples of the present disclosure provide systems and methods relating to a machine comprehension test with a learning-based approach, harnessing neural networks arranged in a parallel hierarchy. This parallel hierarchy enables the model to compare the passage, question, and answer from a variety of perspectives, as opposed to using a manually designed set of features. Perspectives may range from the word level to sentence fragments to sequences of sentences, and networks operate on word-embedding representations of text. A training methodology for small data is also provided.Type: ApplicationFiled: May 12, 2020Publication date: September 3, 2020Applicant: MALUUBA INC.Inventors: Adam Trischler, Zheng Ye, Xingdi Yuan, Philip Bachman
-
Patent number: 10691999Abstract: Examples of the present disclosure provide systems and methods relating to a machine comprehension test with a learning-based approach, harnessing neural networks arranged in a parallel hierarchy. This parallel hierarchy enables the model to compare the passage, question, and answer from a variety of perspectives, as opposed to using a manually designed set of features. Perspectives may range from the word level to sentence fragments to sequences of sentences, and networks operate on word-embedding representations of text. A training methodology for small data is also provided.Type: GrantFiled: March 16, 2017Date of Patent: June 23, 2020Assignee: Maluuba Inc.Inventors: Adam Trischler, Zheng Ye, Xingdi Yuan, Philip Bachman
-
Patent number: 10592607Abstract: Described herein are systems and methods for providing a natural language comprehension system (NLCS) that iteratively performs an alternating search to gather information that may be used to predict the answer to the question. The NLCS first attends to a query glimpse of the question, and then finds one or more corresponding matches by attending to a text glimpse of the text.Type: GrantFiled: June 2, 2017Date of Patent: March 17, 2020Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Alessandro Sordoni, Philip Bachman, Adam Peter Trischler
-
Patent number: 10242667Abstract: Described herein are systems and methods for providing a natural language generator in a spoken dialog system that considers both lexicalized and delexicalized dialog act slot-value pairs when translating one or more dialog act slot-value pairs into a natural language output. Each slot and value associated with the slot in a dialog act are represented as (dialog act+slot, value), where the first term (dialog act+slot) is delexicalized and the second term (value) is lexicalized. Each dialog act slot-value representation is processed to produce at least one delexicalized sentence as an output. A lexicalized sentence is produced by replacing each delexicalized slot with the value associated with the delexicalized slot.Type: GrantFiled: June 2, 2017Date of Patent: March 26, 2019Assignee: Maluuba Inc.Inventors: Shikhar Sharma, Jing He, Kaheer Suleman, Philip Bachman, Hannes Schulz
-
Publication number: 20170352347Abstract: Described herein are systems and methods for providing a natural language generator in a spoken dialogue system that considers both lexicalized and delexicalized dialogue act slot-value pairs when translating one or more dialogue act slot-value pairs into a natural language output. Each slot and value associated with the slot in a dialogue act are represented as (dialogue act+slot, value), where the first term (dialogue act+slot) is delexicalized and the second term (value) is lexicalized. Each dialogue act slot-value representation is processed to produce to produce at least one delexicalized sentence as an output. A lexicalized sentence is produced by replacing each delexicalized slot with the value associated with the delexicalized slot.Type: ApplicationFiled: June 2, 2017Publication date: December 7, 2017Applicant: Maluuba Inc.Inventors: Shikhar Sharma, Jing He, Kaheer Suleman, Philip Bachman, Hannes Schulz
-
Publication number: 20170351663Abstract: Described herein are systems and methods for providing a natural language comprehension system (NLCS) that iteratively performs an alternating search to gather information that may be used to predict the answer to the question. The NLCS first attends to a query glimpse of the question, and then finds one or more corresponding matches by attending to a text glimpse of the text.Type: ApplicationFiled: June 2, 2017Publication date: December 7, 2017Applicant: Maluuba Inc.Inventors: Alessandro Sordoni, Philip Bachman, Adam Peter Trischler
-
Publication number: 20170337479Abstract: Described herein are systems and methods for providing a natural language comprehension system that employs a two-stage process for machine comprehension of text. The first stage indicates words in one or more text passages that potentially answer a question. The first stage outputs a set of candidate answers for the question, along with a first probability of correctness for each candidate answer. The second stage forms one or more hypotheses by inserting each candidate answer into the question and determines whether a sematic relationship exists between each hypothesis and each sentence in the text. The second processing circuitry generates a second probability of correctness for each candidate answer and combines the first probability with the second probability to produce a score that is used to rank the candidate answers. The candidate answer with the highest score is selected as a predicted answer.Type: ApplicationFiled: May 17, 2017Publication date: November 23, 2017Applicant: Maluuba Inc.Inventors: Adam Trischler, Philip Bachman, Xingdi Yuan, Alessandro Sordoni, Zheng Ye
-
Publication number: 20170270409Abstract: Examples of the present disclosure provide systems and methods relating to a machine comprehension test with a learning-based approach, harnessing neural networks arranged in a parallel hierarchy. This parallel hierarchy enables the model to compare the passage, question, and answer from a variety of perspectives, as opposed to using a manually designed set of features. Perspectives may range from the word level to sentence fragments to sequences of sentences, and networks operate on word-embedding representations of text. A training methodology for small data is also provided.Type: ApplicationFiled: March 16, 2017Publication date: September 21, 2017Applicant: Maluuba Inc.Inventors: Adam Trischler, Zheng Ye, Xingdi Yuan, Philip Bachman